Originally posted on The Horizons Tracker. The latest generation of AI have proven themselves incredibly proficient at the kind of tasks we normally associate as being a strength of computers, but doubts remain about their ability to perform more human tasks. It might be a small step, but a small step has indeed been made in this direction, with research1 from BYU highlighting how AI can be used to cooperate and compromise rather than compete. "The end goal is that we understand the mathematics behind cooperation with people and what attributes artificial intelligence needs to develop social skills," the authors say. "AI needs to be able to respond to us and articulate what it's doing. It has to be able to interact with other people."

Winning a competition really can stoke a man's ego – to the extent that they may be more likely to cheat on their partners, a new study suggests. Researchers have found that men experience a testosterone boost when they believe they've bested another man at something, causing some to view themselves as a more valuable'sexual prospect.' And, it all boils down to the belief that they have won, as opposed to the actual effort of the task itself. The study showed that winning causes hormonal fluctuations in men that can influence their sexual behaviour and make them more likely to approach attractive women. Researchers have found that men experience a testosterone boost when they believe they've bested another man at something, causing some to view themselves as a more valuable'sexual prospect.'

We propose approaches based on deep learning to localize objects in images when only a small training dataset is available and the images have low quality. That applies to many problems in medical image processing, and in particular to the analysis of fluoroscopic (low-dose) X-ray images, where the images have low contrast. We solve the problem by incorporating high-level information about the objects, which could be a simple geometrical model, like a circular outline, or a more complex statistical model. A simple geometrical representation can sufficiently describe some objects and only requires minimal labeling. Statistical shape models can be used to represent more complex objects. We propose computationally efficient two-stage approaches, which we call deep morphing, for both representations by fitting the representation to the output of a deep segmentation network.

Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving encouraging empirical success, its underlying mathematical principle on {\em policy-distribution} optimization is unclear. We place policy optimization into the space of probability measures, and interpret it as Wasserstein gradient flows. On the probability-measure space, under specified circumstances, policy optimization becomes a convex problem in terms of distribution optimization. To make optimization feasible, we develop efficient algorithms by numerically solving the corresponding discrete gradient flows. Our technique is applicable to several RL settings, and is related to many state-of-the-art policy-optimization algorithms. Empirical results verify the effectiveness of our framework, often obtaining better performance compared to related algorithms.

Hamiltonian Monte Carlo (HMC) is a very popular and generic collection of Markov chain Monte Carlo (MCMC) algorithms. One explanation for the popularity of HMC algorithms is their excellent performance as the dimension $d$ of the target becomes large: under conditions that are satisfied for many common statistical models, optimally-tuned HMC algorithms have a running time that scales like $d^{0.25}$. In stark contrast, the running time of the usual Random-Walk Metropolis (RWM) algorithm, optimally tuned, scales like $d$. This superior scaling of the HMC algorithm with dimension is attributed to the fact that it, unlike RWM, incorporates the gradient information in the proposal distribution. In this paper, we investigate a different scaling question: does HMC beat RWM for highly $\textit{multimodal}$ targets? We find that the answer is often $\textit{no}$. We compute the spectral gaps for both the algorithms for a specific class of multimodal target densities, and show that they are identical. The key reason is that, within one mode, the gradient is effectively ignorant about other modes, thus negating the advantage the HMC algorithm enjoys in unimodal targets. We also give heuristic arguments suggesting that the above observation may hold quite generally. Our main tool for answering this question is a novel simple formula for the conductance of HMC using Liouville's theorem. This result allows us to compute the spectral gap of HMC algorithms, for both the classical HMC with isotropic momentum and the recent Riemannian HMC, for multimodal targets.

In this paper we investigate the supervised backpropagation training of multilayer neural networks from a dynamical systems point of view. We discuss some links with the qualitative theory of differential equations and introduce the overfly algorithm to tackle the local minima problem. Our approach is based on the existence of first integrals of the generalised gradient system with build-in dissipation.

Spatial separation of suspended particles based on contrast in their physical or chemical properties forms the basis of various biological assays performed on lab-on-achip devices. To electronically acquire this information, we have recently introduced a microfluidic sensing platform, called Microfluidic CODES, which combines the resistive pulse sensing with the code division multiple access in multiplexing a network of integrated electrical sensors. In this paper, we enhance the multiplexing capacity of the Microfluidic CODES by employing sensors that generate non-orthogonal code waveforms and a new decoding algorithm that combines machine learning techniques with minimum mean-squared error estimation. As a proof of principle, we fabricated a microfluidic device with a network of 10 code-multiplexed sensors and characterized it using cells suspended in phosphate buffer saline solution.

Judgment aggregation is a general framework for collective decision making that can be used to model many different settings. Due to its general nature, the worst case complexity of essentially all relevant problems in this framework is very high. However, these intractability results are mainly due to the fact that the language to represent the aggregation domain is overly expressive. We initiate an investigation of representation languages for judgment aggregation that strike a balance between (1) being limited enough to yield computational tractability results and (2) being expressive enough to model relevant applications. In particular, we consider the languages of Krom formulas, (definite) Horn formulas, and Boolean circuits in decomposable negation normal form (DNNF). We illustrate the use of the positive complexity results that we obtain for these languages with a concrete application: voting on how to spend a budget (i.e., participatory budgeting).

Motivated by applications in hyperspectral imaging we investigate methods for approximating a high-dimensional non-negative matrix $\mathbf{\mathit{Y}}$ by a product of two lower-dimensional, non-negative matrices $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}.$ This so-called non-negative matrix factorization is based on defining suitable Tikhonov functionals, which combine a discrepancy measure for $\mathbf{\mathit{Y}}\approx\mathbf{\mathit{KX}}$ with penalty terms for enforcing additional properties of $\mathbf{\mathit{K}}$ and $\mathbf{\mathit{X}}$. The minimization is based on alternating minimization with respect to $\mathbf{\mathit{K}}$ or $\mathbf{\mathit{X}}$, where in each iteration step one replaces the original Tikhonov functional by a locally defined surrogate functional. The choice of surrogate functionals is crucial: It should allow a comparatively simple minimization and simultaneously its first order optimality condition should lead to multiplicative update rules, which automatically preserve non-negativity of the iterates. We review the most standard construction principles for surrogate functionals for Frobenius-norm and Kullback-Leibler discrepancy measures. We extend the known surrogate constructions by a general framework, which allows to add a large variety of penalty terms. The paper finishes by deriving the corresponding alternating minimization schemes explicitely and by applying these methods to MALDI imaging data.

Primary care serves as patients' first point of contact with the healthcare system and is a continuing focal point of comprehensive, accessible, and community-based care [1]. More than just a gate-keeping process for specialist referrals, it has been widely recognized for its focus on caring for the longterm health of patients rather than solely for treating specific diseases or conditions. As such, primary care helps deliver more equitable health outcomes across populations and meets 80-90% of individuals' health needs throughout their lives [2]. To this end, a recent special report from the Economist stated that "good primary care is an essential precondition for a decent healthcare system" [3]. The World Health Organization (WHO) emphasized several defining features for effective and socially productive primary care, including comprehensiveness, person-centeredness, and continuity of care [4]. In particular, person-centeredness refers to the "clinical method of participatory democracy" that allows patients to participate in decisions that affect their health.